The Alan Turing Institute
Delft University of Technology
2024-05-08
Economist by training, previously Bank of England, currently 3rd year PhD in Trustworthy AI @ TU Delft.
Why Trustworthy AI and why in Julia?
Taija is the organization that hosts software geared towards Trustworthy Artificial Intelligence in Julia.
The TaijaBase.jl package provides common symbols, types and functions that are used across all or multiple Taija packages.
CounterfactualExplanations.jl and LaplaceRedux.jl at JuliaCon.ConformalPrediction.jl at JuliaCon.CounterfactualExplanations.jl and LaPlaceRedux.jl.CounterfactualExplanations.jl published in JuliaCon proceedings.CounterfactualExplanations.jl and LaplaceRedux.jl at JuliaCon.TaijaInteractive.jl.ConformalPrediction.jl at JuliaCon.CounterfactualExplanations.jl and LaPlaceRedux.jl.CounterfactualExplanations.jl published in JuliaCon proceedings.CounterfactualExplanations.jl and LaplaceRedux.jl at JuliaCon.Taija has been used in the following publications:
CounterfactualExplanations.jl: A package for Counterfactual Explanations and Algorithmic Recourse in Julia.
\[ \begin{aligned} \min_{\mathbf{Z}^\prime \in \mathcal{Z}^L} \{ {\text{yloss}(M_{\theta}(f(\mathbf{Z}^\prime)),\mathbf{y}^+)} + \lambda {\text{cost}(f(\mathbf{Z}^\prime)) } \} \end{aligned} \]
Counterfactual Explanations (CE) explain how inputs into a model need to change for it to produce different outputs.
📜 Altmeyer, Deursen, et al. (2023) @ JuliaCon 2022.
All of these counterfactuals are valid explanations for the model’s prediction.
Which one would you pick?
Figure 2: Turning a 9 into a 7: Counterfactual explanations for an image classifier produced using Wachter (Wachter, Mittelstadt, and Russell 2017), Schut (Schut et al. 2021) and REVISE (Joshi et al. 2019).
📜 Altmeyer, Farmanbar, et al. (2023) @ AAAI 2024
Key Idea
Use the hybrid objective of joint energy models (JEM) and a model-agnostic penalty for predictive uncertainty: Energy-Constrained (\(\mathcal{E}_{\theta}\)) Conformal (\(\Omega\)) Counterfactuals (ECCCo).
ECCCo objective1:
\[ \begin{aligned} & \min_{\mathbf{Z}^\prime \in \mathcal{Z}^L} \{ {L_{\text{clf}}(f(\mathbf{Z}^\prime);M_{\theta},\mathbf{y}^+)}+ \lambda_1 {\text{cost}(f(\mathbf{Z}^\prime)) } \\ &+ \lambda_2 \mathcal{E}_{\theta}(f(\mathbf{Z}^\prime)|\mathbf{y}^+) + \lambda_3 \Omega(C_{\theta}(f(\mathbf{Z}^\prime);\alpha)) \} \end{aligned} \]
ConformalPrediction.jl: A package for Predictive Uncertainty Quantification through Conformal Prediction for Machine Learning models trained in MLJ.
Intuitively, CP works under the premise of turning heuristic notions of uncertainty into rigorous uncertainty estimates through repeated sampling or the use of dedicated calibration data.
Conformal Prediction in action: prediction intervals at varying coverage rates. As coverage grows, so does the width of the prediction interval.
ConformalPrediction.jl meets SymbolicRegression.jl.
LaplaceRedux.jl: A package for Effortless Bayesian Deep Learning through Laplace Approximation for Flux.jl neural networks.
We want BMA for neural networks,
\[ p(y|x,\mathcal{D}) = \int p(y|x,\theta)p(\theta|\mathcal{D})d\theta \tag{1}\]
where \(p(y|x,\theta)\) is the likelihood, \(p(\theta|\mathcal{D})\) is the posterior and \(\mathcal{D}\) is the training data.
JointEnergyModels.jl: A package for Joint Energy Models and Energy-Based Models in Julia.
Contributions welcome!
Transformers.jl).